Data · dataset · 2025
A dataset comparing the performance of a publicly available generative artificial intelligence chatbot and its customised version in providing first aid guidance for seizures
Listed in Teesside University Research Data Repository
The applicability of generative artificial intelligence chatbots as first aid consultants is a topical issue.
Description
This dataset contains the results of an analysis comparing the quality of seizure first aid recommendations generated by the publicly available chatbot ChatGPT (GPT-4o model) with those generated by its customised version. The dataset consists of three files.
The first file (customisation rules.txt) contains customised text instructions for the chatbot, including definitions of key terms and roles, communication and dialogue style guidelines, a catalogue and description of knowledge base documents, operational recommendations for applying knowledge base documents in dialogue, prohibited actions, barrier mitigation strategies, chatbot phrasing examples, and conversation closure instructions.
Read the rest (2 more)
The second file (instructions.txt) contains four sets of mandatory questions and instructional wordings corresponding to the following emergency scenarios: scenario I – an unconscious victim with ongoing seizures; scenario II – a victim in the postictal period, unconscious, not breathing; scenario III – a victim in the postictal period, unconscious, breathing normally; scenario IV – a victim in the postictal period, conscious.
The third file (evaluation results.xlsx) contains the results of a comparative analysis of the effectiveness of the publicly available chatbot (Baseline_# sheets) and its customised version (Custom_# sheets) according to checklists corresponding to the dialogue scenarios.
Links
Where it is published
- DOI doi.org/10.17632/6h53jrhf7t.1 ↗
DOI / persistent id · from researchdata tees ac uk
Catalogue records · 1
- OAI-PMH record data.mendeley.com/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai%3Adata… ↗
metadata API · from researchdata tees ac uk
Topics
- From keywords
- Artificial intelligence · Computer Science & AI · Earth & Environmental Science · Engineering · Humanities
- Inferred from text
- Text 75%
Provenance · 1 source records, 11 field assertions
| Source | Key | Last seen | Raw |
|---|---|---|---|
| Teesside University Research Data Repository | oai:data.mendeley.com/6h53jrhf7t.1 | 16 h ago | JSON v1 |
| Field | Assertion | Extractor | Evidence |
|---|---|---|---|
| access_level | source · researchdata tees ac uk | connector:researchdata_tees_ac_uk@1.0.0 | |
| concepts[field].anzsrc:group:4602 | mapping · researchdata tees ac uk | vocabulary-mapper@1.0.0 | keywords['Artificial Intelligence'] |
| concepts[field].local:field:computer-science-ai | mapping · researchdata tees ac uk | connector:researchdata_tees_ac_uk@1.0.0 | |
| concepts[field].local:field:earth-environmental | mapping · researchdata tees ac uk | connector:researchdata_tees_ac_uk@1.0.0 | |
| concepts[field].local:field:engineering | mapping · researchdata tees ac uk | connector:researchdata_tees_ac_uk@1.0.0 | |
| concepts[field].local:field:humanities | mapping · researchdata tees ac uk | connector:researchdata_tees_ac_uk@1.0.0 | |
| concepts[modality].local:modality:text | enrichment · researchdata tees ac uk | keyword-concept-rules@1.0.0 | title+description (75%) |
| description | source · researchdata tees ac uk | connector:researchdata_tees_ac_uk@1.0.0 | /metadata/dc/description |
| license | source · researchdata tees ac uk | connector:researchdata_tees_ac_uk@1.0.0 | /metadata/dc/rights |
| publication_date | source · researchdata tees ac uk | connector:researchdata_tees_ac_uk@1.0.0 | |
| title | source · researchdata tees ac uk | connector:researchdata_tees_ac_uk@1.0.0 | /metadata/dc/title |